vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

tts : add OuteTTS support (#10784)

Browse source 
* server : add "tokens" output

ggml-ci

* server : output embeddings for all tokens when pooling = none

ggml-ci

* server : be explicit about the pooling type in the tests

ggml-ci

* server : do not normalize embeddings when there is no pooling

ggml-ci

* llama : add OuteTTS support (wip)

* wip

* extract features

* first conv

* group norm

* resnet conv

* resnet

* attn

* pos net

* layer norm

* convnext

* head

* hann window

* fix n_embd + remove llama.cpp hacks

* compute hann window

* fft

* spectrum processing

* clean-up

* tts : receive input text and generate codes

* clip : fix new conv name

* tts : minor fix

* tts : add header + minor fixes

ggml-ci

* tts : add matchematical constant

ggml-ci

* tts : fix sampling + cut initial noise

* tts : fixes

* tts : update default samplers

ggml-ci

* tts : text pre-processing

* tts : outetts-voc -> wavtokenizer-dec

* tts : remove hardcoded constants

ggml-ci

* tts : fix tensor shapes

* llama : refactor wavtokenizer tensors

ggml-ci

* cont

ggml-ci

* cont [no ci]

* llama : update WavTokenizer to non-causal attn

* llama : handle no-vocab detokenization

* tts : add Python example for OuteTTS (wip)

* tts : extend python example to generate spectrogram

ggml-ci

* server : fix rebase artifacts

* tts : enable "return_tokens" in Python example

ggml-ci

* tts : minor fixes

* common : support HF download for vocoder
This commit is contained in:
Georgi Gerganov 2024-12-18 19:27:21 +02:00 • committed by GitHub
parent 7bbb5acf12
commit 0bf2d10c55
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 2509 additions and 532 deletions
Download patch file Download diff file Expand all files Collapse all files

6
examples/llava/clip.cpp
View file

@ -896,7 +896,7 @@ static ggml_cgraph * clip_image_build_graph(clip_ctx * ctx, const clip_image_f32
mlp_3 = ggml_cont(ctx0, ggml_permute(ctx0, mlp_3, 1, 0, 2, 3));
mlp_3 = ggml_reshape_4d(ctx0, mlp_3, n_patch, n_patch, mlp_3->ne[1], mlp_3->ne[2]);
// stride = 1, padding = 1, bias is nullptr
block_1 = ggml_conv_depthwise_2d(ctx0, model.mm_model_block_1_block_0_0_w, mlp_3, 1, 1, 1, 1, 1, 1);
block_1 = ggml_conv_2d_dw(ctx0, model.mm_model_block_1_block_0_0_w, mlp_3, 1, 1, 1, 1, 1, 1);
// layer norm
// // block_1 shape = [1, 2048, 24, 24], ne = [24, 24, 2048, 1]
@ -944,7 +944,7 @@ static ggml_cgraph * clip_image_build_graph(clip_ctx * ctx, const clip_image_f32
// block_2
{
// stride = 2
block_1 = ggml_conv_depthwise_2d(ctx0, model.mm_model_block_2_block_0_0_w, block_1, 2, 2, 1, 1, 1, 1);
block_1 = ggml_conv_2d_dw(ctx0, model.mm_model_block_2_block_0_0_w, block_1, 2, 2, 1, 1, 1, 1);
// block_1 shape = [1, 2048, 12, 12], ne = [12, 12, 2048, 1]
// layer norm
@ -1005,7 +1005,7 @@ static ggml_cgraph * clip_image_build_graph(clip_ctx * ctx, const clip_image_f32
// mlp_2 ne [24, 24, 2048, 1]
mlp_2 = ggml_pool_2d(ctx0, mlp_2, GGML_OP_POOL_AVG, 2, 2, 2, 2, 0, 0);
// weight ne = [3, 3, 2048, 1]
struct ggml_tensor * peg_0 = ggml_conv_depthwise_2d(ctx0, model.mm_model_peg_0_w, mlp_2, 1, 1, 1, 1, 1, 1);
struct ggml_tensor * peg_0 = ggml_conv_2d_dw(ctx0, model.mm_model_peg_0_w, mlp_2, 1, 1, 1, 1, 1, 1);
peg_0 = ggml_cont(ctx0, ggml_permute(ctx0, peg_0, 1, 2, 0, 3));
peg_0 = ggml_add(ctx0, peg_0, model.mm_model_peg_0_b);
mlp_2 = ggml_cont(ctx0, ggml_permute(ctx0, mlp_2, 1, 2, 0, 3));